Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles that indicate ongoing actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bal
    -0.75
    eka
    -0.73
    she
    -0.69
    peria
    -0.68
    aura
    -0.67
    lat
    -0.66
    cia
    -0.64
    antha
    -0.63
    redo
    -0.63
    phal
    -0.63
    POSITIVE LOGITS
    GGGGGGGG
    0.77
     lifestyles
    0.68
     Squid
    0.66
     ducks
    0.66
     stuff
    0.66
     crap
    0.64
     rods
    0.64
     threats
    0.63
     lately
    0.62
     noises
    0.62
    Act Density 0.409%

    No Known Activations